Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 22090
    Prev
    Next
    INDEX
    Explanations

    words related to notable individuals, especially in sports or politics

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or short forms typically used in specific contexts, particularly in sports or identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TAG
    -0.73
    ĨĴ
    -0.71
    Preview
    -0.70
    taboola
    -0.70
    NECT
    -0.68
    é¾
    -0.66
    EMA
    -0.65
    FUL
    -0.64
    ĻĤ
    -0.63
    IRO
    -0.63
    POSITIVE LOGITS
    abase
    0.87
    hy
    0.78
    aya
    0.68
     Tale
    0.66
    shire
    0.66
    utsche
    0.65
    hai
    0.64
    utsch
    0.63
    geons
    0.61
    illet
    0.61
    Activations Density 0.252%

    No Known Activations